Skip to main content
Glama
Antigravity Desktop MCP

Antigravity Desktop MCP

by silas-ouyang

desktop_paste

Pastes long or multi-line Unicode text by writing it to the clipboard and sending Ctrl+V, while saving and restoring previous clipboard contents.

Instructions

Paste long or multi-line Unicode text reliably via clipboard + Ctrl+V, automatically saving & restoring previous clipboard contents (use require_restore: true to refuse if clipboard contains non-text data).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "desktop_paste"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
verifyNo
restoreNo
into_hwndNo
require_restoreNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds real behavior beyond the annotations: clipboard contents are automatically saved and restored, and `require_restore: true` will refuse the operation if the clipboard holds non-text data. That refusal semantics and the clipboard-restore guarantee are exactly the side effects an agent needs to know for a mutation tool, though it never says which window receives the paste when no target is given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the core action and mechanism, then appends the restore caveat. No wasted words, though the parenthetical packs the only parameter guidance into a trailing clause rather than giving it structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and five undocumented parameters, the description should carry more of the load. The clipboard save/restore and refusal behavior are well covered, but window targeting and the `verify` payload remain unexplained, which matters for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across five parameters, and the description only explains `require_restore` (and implies `restore`). `into_hwnd` (target window selection) and `verify` (a nested object) are completely undocumented in both schema and prose, forcing the agent to guess at their meaning and format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (paste), the resource (long or multi-line Unicode text), and the mechanism (clipboard + Ctrl+V). The 'long or multi-line Unicode' framing implicitly separates it from character-by-character typing tools, but no sibling is named explicitly, so differentiation is left partly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'long or multi-line Unicode text' functions as an implied when-to-use condition, and the parenthetical gives a concrete rule for `require_restore`. However, there is no explicit statement of when NOT to use it or which sibling (e.g. desktop_type, desktop_key) handles short or keyboard-shortcut input.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.